Entity-Augmented Distributional Semantics for Discourse Relations
This work addresses a key problem in natural language processing for improving text coherence analysis, though it is incremental by building on existing compositional distributional semantics.
The paper tackled the challenge of automatically identifying discourse relations by incorporating entity-level semantics, resulting in substantial improvements over the previous state-of-the-art on the Penn Discourse Treebank.
Discourse relations bind smaller linguistic elements into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked sentences. A more subtle challenge is that it is not enough to represent the meaning of each sentence of a discourse relation, because the relation may depend on links between lower-level elements, such as entity mentions. Our solution computes distributional meaning representations by composition up the syntactic parse tree. A key difference from previous work on compositional distributional semantics is that we also compute representations for entity mentions, using a novel downward compositional pass. Discourse relations are predicted not only from the distributional representations of the sentences, but also of their coreferent entity mentions. The resulting system obtains substantial improvements over the previous state-of-the-art in predicting implicit discourse relations in the Penn Discourse Treebank.